22 results about "Color constancy" patented technology

The invention discloses a semi-supervised non-contact neonatal jaundice home intelligent early warning method based on image calibration, and the method comprises the steps: building a camera response function database, and building a color constancy depth model and a skin region segmentation network; designing a strong and weak enhancement strategy by using a large amount of label-free home data, constructing a time and context comparison learning module, and performing self-supervised training on a feature encoder; a small amount of labeled hospital data and a large amount of unlabeled family data are combined, and semi-supervised fine tuning is realized through pseudo label generation and supervised comparative learning; image sequences continuously uploaded by a user are input into the model, multi-day prediction of the bilirubin level is achieved, prediction uncertainty is quantified in combination with a Bayesian method, the risk boundary is dynamically adjusted, and personalized early warning is provided. According to the method, a user does not need to use a physical colorimetric card, color measurement errors caused by model differences of mobile equipment and variability of household illumination are inhibited from a data source, and the accuracy and robustness of subsequent jaundice assessment are improved; through a training framework combining self-supervised pre-training and semi-supervised fine tuning, the understanding ability and generalization performance of the model for the sequential characteristics of jaundice are improved.

The invention provides a method executed by electronic equipment, the electronic equipment, a storage medium and a program product. The method comprises the steps of obtaining a first image; performing illumination prediction on the first image through a first AI model to obtain a second image; wherein the first AI model is obtained by training based on training data including a sample image acquired for an object under an illumination condition, and a first real image and a second real image corresponding to the sample image; wherein the first real image is related to the illumination of the collected sample image, and the second real image is related to the color presented by the object in the sample image. The accuracy of illumination prediction can be improved on the basis of solving the problem of color constancy. Optionally, the method executed by the electronic equipment can be executed by using an artificial intelligence model.

A system, apparatus, and method for processing an image based on color constancy are provided herein. The method comprises the following steps: obtaining an image in a first color space; converting the image into data in a second color space; transforming the data using color adaptation; performing a first normalization on the transformed data, wherein the first normalization includes applying a dynamic spatial filtering technique to adjust the transformed data based on the light intensity; applying a set of filters to the normalized data, wherein the set of filters are convolved based on the normalized data associated with the image; performing a second normalization on the filtered data to obtain an illumination estimate of the image related to the filtered data; and outputting normalized data from the second normalization, where the normalized data maintains color constancy based on the illumination estimate, thereby removing illumination from the normalized data.

This invention discloses a method for detecting the freshness of giant salamander meat based on color constancy and integrated intelligent vision, belonging to the fields of food safety and computer vision technology. The method includes: acquiring RAW images of the meat sample and an indicator film and resolving them into linear radiosity tensors; constructing a color correction model using a latent diffusion local redraw network and a conditional control network; synthesizing a structure-constrained virtual reference color card in a masked region; extracting ambient light source features and performing adaptive white balance compensation to output a standard color image; inputting this image into a deep network optimized by ArcFace to extract a high-dimensional feature vector; and finally inputting this vector into an XGBoost model to fit a nonlinear decision boundary and outputting a freshness rating. This invention effectively reduces color shift interference from complex light sources, improves the recognition accuracy of samples in the critical period of color change, and provides a highly robust solution for non-destructive monitoring of giant salamander meat freshness in actual market environments.

The application discloses an indoor scene-oriented color constancy algorithm error evaluation prediction method and system, and belongs to the technical field of computer and information service. The application comprises the following steps: acquiring an indoor scene color constancy dataset containing portrait content; acquiring real light source color information of a color cast image in the dataset; acquiring estimated light source color information obtained based on a color constancy algorithm to be evaluated; performing color space conversion on the light source color information; for the color constancy algorithm to be evaluated, corresponding estimated values are obtained according to the real light source color attribute, the estimated light source color attribute and a color constancy algorithm error evaluation quantitative model, so that the light source color estimation accuracy of different color constancy algorithms is represented. The application realizes high-precision and high-stability error evaluation of the color constancy algorithm for the indoor scene containing the portrait content.

Embodiments of this disclosure can provide a system and method for white balancing images. During operation, the system can obtain labeled red, green, and blue (RGB) image samples captured by a plurality of cameras and generate a plurality of training tasks. A respective training task is associated with RGB image samples captured by a corresponding camera. The system can perform meta-training over the plurality of training tasks to obtain a meta model, with parameters of the meta model optimized based on a global loss function. The system can obtain an image captured by a first camera, fine-tune the meta model using labeled RGB image samples captured by the first camera to obtain a fine-tuned model specific to the first camera, and implement the fine-tuned model to white balance the image.

The invention discloses a vertical plastic laying machine for saline-alkali soil sealing and a plastic laying monitoring method based on machine vision, and belongs to the technical field of salt isolating membrane laying. The vertical plastic laying machine for saline-alkali soil sealing comprises a chain type furrow opener, a membrane placing mechanism and an industrial camera; the membrane placing mechanism realizes smooth laying of the isolating membrane through a membrane releasing roller, a guide roller, a vertical roller and a guide plate, and an industrial camera monitors in real time. According to the invention, isolation membrane laying and real-time quality management and control can be realized, and the operation efficiency and the treatment effect are improved. The plastic laying monitoring method based on machine vision comprises the steps that an isolating membrane image in the laying process is collected, and a corrected and enhanced image is obtained through self-adaptive illumination elimination processing; extracting illumination invariant features fusing multi-channel color constancy and gradient magnitude; a multi-scale residual error is calculated, and a defect sensitive feature graph is generated through morphological topological weight modulation; and in combination with real-time tension fluctuation, four states of normality, wrinkling, hemming and damage are identified.

The application relates to a convolutional neural network-based sequence image color constancy calculation method, which comprises the following steps: reading an original image sequence by using a preset composite model, performing image correction and cutting on the original image sequence to obtain a to-be-processed image sequence meeting preset image standard conditions; performing preset transformation processing on key frame images of the to-be-processed image sequence to obtain a simulation image sequence; extracting a first image feature sequence from the original image sequence and a second image feature sequence from the simulation image sequence by using two preset convolutional neural networks; processing the first image feature sequence and the second image feature sequence by using a gated recurrent unit (GRU) to output a first tensor and a second tensor; and generating three channels corresponding to an RGB color space based on a splicing tensor of the first tensor and the second tensor, so as to generate light source information for correcting image colors according to the three-channel features.

The invention discloses an industrial camera color constancy correction device system based on image cluster block expansion convolution. The industrial camera color constancy correction device system comprises a PC end module and a camera end module. The PC end module completes training and optimization of an illumination model, and the camera end module realizes real-time reasoning and white balance correction through an embedded hardware FPGA (Field Programmable Gate Array); the construction method for generating the lightweight illumination estimation training model by the PC end module specifically comprises the following steps: step 1, expanding a data set; 2, constructing a sectional type multi-scale expansion convolutional network model; step 3, training the expanded data set obtained in the step 1 by using the segmented multi-scale expansion convolutional network model constructed in the step 2, and iteratively training parameters; color constancy data analysis dimensions are added, image data are analyzed from two dimensions of expanding a data set and constructing a lightweight illumination estimation training model, the average angle error in an industrial scene is reduced to 1.52 degrees, the frame rate is larger than or equal to 30 fps, power consumption is smaller than 2 W, and the method has the characteristics of high precision and low delay.

This invention relates to an image color correction method, system, and electronic device based on a dual-discriminator network. To address the limitations imposed on the learning capabilities of GANs in color constancy tasks by issues such as color feature misleading and the low sensitivity of the discriminator to color information, we propose a Dual-Discriminator Generative Adversarial Network (DDGAN). It comprises a basic generative adversarial network and a Feature Fusion Discriminator (FFD) module. The FFD is a discriminator module with two feature extraction branches: one extracts color features, and the other extracts globally relevant features. The FFD fuses these features together to weaken structural features and enhance the discriminator's sensitivity to color features. Finally, to obtain a more uniform color and content image, a global consistency constraint is applied to the structural features weakened by the FFD, unifying the structural and color features, ultimately resulting in a high-precision image color correction method.

The invention discloses a video monitoring image management method and device, equipment and a medium, and relates to the technical field of image management, and the method comprises the steps: obtaining a video monitoring image through a target video camera; performing white balance processing by using a preset color constancy algorithm to generate a white balance image of the video monitoring image; vectorizing the white balance image based on a preset feature network to extract an image feature value, and judging whether a target image vector exists in a preset vector database by using a preset nearest neighbor search algorithm; and if the video monitoring image does not exist, storing the image characteristic value in a preset vector database, storing the video monitoring image in a preset image database, and constructing a vector index so as to establish a unique mapping relationship between the image characteristic value in the preset vector database and the video monitoring image in the preset image database through the vector index. Therefore, the management method of the video monitoring image can be optimized to eliminate the illumination influence and reduce the false drop rate of the image.

In order to restore the real color of the object in the image in the human eye due to the illumination color of different ambient light changing the color of the object in the image scene, the application discloses a color constancy algorithm based on gray surface extraction, which extracts the gray pixels in the image based on the illumination invariant vector, then uses the gray world algorithm on the pixels to predict the light source in the image, and corrects the color adaptation of the image. According to the color adaptation result, the gray pixels in the image are continuously detected and the color adaptation is carried out through iterative circulation until the set threshold is met, and the algorithm is stopped. Compared with the traditional algorithm, the illumination estimation accuracy is greatly improved.

This invention discloses a multi-source color constancy method and system based on color decoupling. It utilizes a pixel-level multi-source color constancy model to achieve multi-source color constancy, including a Content Color Awareness (CCAM) module and a Contrast Coordination (CHAM) module. CCAM learns prior color features of scene content, separating scene content color from illumination color by providing the model with these color features, thus reducing the prediction of out-of-gamut light sources. CHAM leverages spatial correlation to make the model more sensitive to the relationships between adjacent features and uses illumination disparity to guide feature classification; it improves local edge contrast by enhancing the uniqueness of homogeneous illumination features and the distinguishability of heterogeneous illumination features; and it further enhances local contrast by assigning fine-grained edge coefficients to emphasize the soft distinguishability of similar illumination features. This invention achieves high-precision multi-source color constancy by introducing advanced semantic information to assist the model in understanding the scene and optimizing feature representation through fine-grained feature constraints.

A cataract classification method based on color invariance and frequency domain attention belongs to the technical field of computer vision and medical artificial intelligence, takes an eye image photographed by a slit lamp as an input data source, constructs a CFC-Mamba classification network integrating a color invariance fusion module and a frequency domain channel attention module, so that the model can effectively extract color robust features which are invariant to devices and enhance the high-frequency detail perception ability to the cataract lesion boundary, adopts color invariance convolution and cross attention fusion mechanism to solve the color offset problem caused by different imaging devices and ensure the cross-device robustness of feature extraction, and through the frequency domain channel attention module, combines Fourier transform, high-pass filtering and double-path channel attention strategy to highlight the high-frequency features of the lesion boundary and improve the fine-grained feature expression ability, and provides a cataract classification system based on color invariance and frequency domain attention. The present application realizes high-precision classification of multi-granularity cataracts.

The invention provides an endoscope image enhancement method and endoscope image enhancement equipment, and relates to the technical field of image processing. According to the invention, the adaptive color constancy loss function calculated based on the first brightness adaptive weight map in the Lab color space is designed, and the adaptive exposure control loss function calculated based on the second brightness adaptive weight map is designed; the image enhancement network is trained based on the self-adaptive color constancy loss function and the self-adaptive exposure control loss function, so that the trained image enhancement network provided by the embodiment of the invention can be based on the to-be-enhanced endoscope image; adaptive learning is carried out to generate a multi-channel curve parameter graph containing a group of pixel-level brightness enhancement curve parameters, and the group of pixel-level brightness enhancement curve parameters corresponding to each pixel point in the multi-channel curve parameter graph is applied to the endoscope image to be enhanced. And the brightness contrast level is maintained while the color fidelity of the enhanced endoscope image to be enhanced is improved.

This invention proposes a semantically preserved color constancy method and system. Leveraging the crucial role of memory color in human color constancy, this method incorporates semantics into color constancy by using a pre-trained classification model on the ImageNet dataset as network initialization parameters. A Semantic Constraint Module (SCM) is designed to measure the feature differences between the color constancy model and the pre-trained model using feature similarity loss, ensuring the network continuously learns semantic knowledge during training and preventing semantic forgetting. An Auxiliary Calibration Module (ACM) is also designed, using small local regions as auxiliary input to enhance features in non-semantic regions with limited intrinsic color ranges, and avoiding potential biases through local-global consistency constraints. This invention achieves high-precision color constancy without increasing inference computation by guiding the correction of low-level color features with high-level semantic information.

The application discloses an outdoor scene-oriented color constancy algorithm error evaluation prediction method and system, and belongs to the technical field of computer and information service. The application comprises the following steps: acquiring an outdoor scene color constancy dataset under natural daylight illumination; acquiring real light source color information of a color cast image in the color constancy dataset; acquiring estimated light source color information calculated based on a color constancy algorithm to be evaluated; performing color space conversion on the light source color information; for the color constancy algorithm to be evaluated, corresponding estimated values are obtained according to real light source color attributes, estimated light source color attributes and a color constancy algorithm error evaluation quantitative model, so that the light source color estimation accuracy of different color constancy algorithms is represented. The application realizes high-precision and high-stability error evaluation of the color constancy algorithm for the outdoor scene under natural daylight illumination.

This invention discloses a method for simultaneous detection of bilirubin and hemoglobin concentrations based on a single-frame image of the eye, comprising: acquiring an image containing a color chart and the eye under a standard light source; performing manual white balance and color correction matrix transformation based on the color chart; extracting the sclera and lower eyelid regions using a YOLOv8 segmentation network; inputting the left and right eye regions into a twin-Swin-Transformer network with shared weights; obtaining predicted values ​​through multi-scale feature fusion and a regression head; and introducing a feature consistency loss optimization model. This invention achieves high-precision simultaneous non-invasive detection of bilirubin and hemoglobin, with advantages such as good color constancy, strong anti-interference ability, and high clinical application value.

The invention relates to a knowledge distillation-based color constancy calculation method, which comprises the following steps of: S1, training a teacher network to realize image illumination color estimation; s2, distilling and training the student network, and migrating the illumination color estimation capability of the teacher network to the student network with a simple structure and a small number of parameters by using a distillation technology; s3, performing fine tuning to train the student network; and S4, realizing calculation color constancy, inputting test image data into the fine-tuned model to estimate the color of the light source, and further obtaining an image after color correction through an ISP process. The problem of dependence on large-scale labeled data when a special deep learning model is constructed for the image sensor is effectively solved, and the requirements for calculation and storage resources are reduced. An efficient and simple student model can be obtained, and possibility is provided for actual deployment in embedded equipment and an image signal processor chip.

The invention discloses a road defect detection method based on a dynamic learning prototype and weak supervised semantic segmentation, and the method obtains an accurate recognition result through enhancing the features reflected in a feature map obtained from an FPN, achieves the recognition accuracy of a full supervised semantic segmentation model, and also achieves the recognition accuracy of a weak supervised semantic segmentation model. And the method has the advantage of low manual annotation cost of the weak supervision semantic segmentation model. In addition, by setting data processing steps of a color constancy algorithm and a channel-space double-attention algorithm, misjudgment of a road defect recognition result caused by light interference and feature discretization in a zoning process are avoided, and the accuracy of the road defect recognition result is improved. And meanwhile, the interference of other objects appearing in the image on the defect identification result is avoided through the superposition of the binary masks. According to the method, not only is the distribution range of the road defects given, but also the thermodynamic diagram of the defect distribution can be obtained, so that detection personnel have more perfect cognition and more accurate grasp on the defect structure.

The application discloses a color constancy calculation method based on human visual mechanism quantitative modeling, comprising the following steps: based on the spatial local brightness contrast, the original image is recursively propagated to obtain a color correction image based on the spatial local contrast mechanism; scene light source information is estimated by using a maxRGB model, a von Kries diagonal gain matrix is constructed to perform global illumination compensation, and a global color correction image is obtained; a fully connected conditional random field model is constructed, two kinds of correction images are used as prior information of a unary potential function of an energy function, and a global correlation between pixels is modeled by a binary potential function; and finally, a final color correction image is obtained through joint optimization and approximate inference of the energy function. The application realizes unified modeling and relative contribution quantification of color adaptation, spatial local contrast and global light source prediction mechanism, improves the accuracy, interpretability and cross-scene robustness of color constancy calculation, and can be applied to the fields of image enhancement, visual perception and intelligent imaging.

The invention discloses a color constancy method based on a color cast perception condition diffusion model. The color constancy method comprises the following steps: firstly, separating color channels from an image with color cast and a reference image by adopting an LCH color space; designing a color offset estimation module to obtain an offset estimation result; taking a color channel as a condition for reverse reconstruction of a diffusion model, and putting an offset estimation result into a U-net network of a conditional diffusion model to guide generation of an image; and performing a color reconstruction process, and finally generating an image after color cast removal. And finally, designing a loss function, finally obtaining a high-quality image after color cast is removed from the color cast image, and realizing a color constancy result, the problems of insufficient color correction and poor color cast and texture detail expression in a multi-light-source environment in the prior art are solved, and the overall effect in an advanced vision task is remarkably improved.